Brief Analysis on Typical Image Saliency Detection Methods
Wenwen Pan, Xiaofei Sun, Xia Wang, Wei Zhang · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2015
Image saliency detection is becoming more and more important in the field of computer vision.The purpose is to detect salient objects in complex background, at the same time, reduce time complexity to get salient objects with high-resolution and clear edge.In this paper some brief analysis on the state-of-the-art studies relating to image saliency detection has been implemented at first.Next, two kinds of the relating methods has been separated, the former is based on space domain and the latter is based on frequency domain.And then some typical methods respective in space domain and frequency domain are introduced and tested in image databases used for image saliency detection, the experimental results of these method are analyzed with running time and saliency map and the results of image segmentation using fixed threshold and adaptive threshold are compared.Finally, the conclusion and prospects of studies on image saliency detection are proposed.